Skip to main content
Glama
HasData

Google Flights MCP Server

Google Flights MCP Server

一个托管的 Model Context Protocol (MCP) 服务器,为 Claude、Cursor、Windsurf 以及任何其他 MCP 客户端提供一个 Google Flights 工具。可以搜索单程、往返和多城市行程,返回票价、航段、碳排放和价格历史,全部以结构化 JSON 呈现;无需 Google 账号,也无须处理已停用的旅行 API。

https://mcp.hasdata.com/api/mcp?apis=google_travel_flights

Glama score tool contract MCP Tools npm PyPI License

目录

Related MCP server: SkyOdyssey MCP

你需要什么

一个 MCP 客户端,以及从控制台获取的 HasData API 密钥;免费创建,无需银行卡,以 15 积分/次的费率计算,试用额度大约可覆盖 66 次调用。这是一个远程服务器,因此最简单的接入方式就是一个 URL 和 x-api-key 请求头,无需运行容器,整个流程中也不涉及 Google 账号。只支持 stdio 的客户端可以通过一个轻量启动器(launcher)访问它;该启动器以 @hasdata/google-flights-mcp 发布在 npm 上,以 hasdata-google-flights-mcp 发布在 PyPI 上,如下所示。

快速开始

服务器 URL 对所有客户端都一样。我们已在 Claude Code 和 Claude Desktop 中实际运行过。其他配置块遵循各客户端自己文档中规定的远程服务器格式。

字段

URL

https://mcp.hasdata.com/api/mcp?apis=google_travel_flights

传输方式

HTTP、可流式传输

认证头

x-api-key: HASDATA_API_KEY

支持 OAuth 的客户端可以将相同的 URL 作为连接器添加,然后直接登录,无需在配置文件中填入密钥。

claude mcp add --transport http google-flights "https://mcp.hasdata.com/api/mcp?apis=google_travel_flights" \
  --header "x-api-key: HASDATA_API_KEY"

依次进入设置(Settings)、连接器(Connectors)、添加自定义连接器(Add custom connector),然后粘贴 https://mcp.hasdata.com/api/mcp?apis=google_travel_flights 并登录。

对于使用配置文件的路线,Claude Desktop 只加载本地(stdio)服务器,因此它通过一个 stdio 启动器访问远程服务器。@hasdata/google-flights-mcp 包就是这个启动器,它会从环境中读取密钥。将它添加到 claude_desktop_config.json

{
  "mcpServers": {
    "google-flights": {
      "command": "npx",
      "args": ["-y", "@hasdata/google-flights-mcp"],
      "env": { "HASDATA_API_KEY": "YOUR_KEY" }
    }
  }
}

若使用 Python 而非 Node,可将启动器换成 PyPI 包,uvx 无需手动安装即可运行它:

{
  "mcpServers": {
    "google-flights": {
      "command": "uvx",
      "args": ["hasdata-google-flights-mcp"],
      "env": { "HASDATA_API_KEY": "YOUR_KEY" }
    }
  }
}

~/.cursor/mcp.json 用于所有项目,或 .cursor/mcp.json 用于单个项目:

{
  "mcpServers": {
    "google-flights": {
      "url": "https://mcp.hasdata.com/api/mcp?apis=google_travel_flights",
      "headers": { "x-api-key": "HASDATA_API_KEY" }
    }
  }
}

~/.codeium/windsurf/mcp_config.json。Windsurf 将该字段称为 serverUrl,而不是 url

{
  "mcpServers": {
    "google-flights": {
      "serverUrl": "https://mcp.hasdata.com/api/mcp?apis=google_travel_flights",
      "headers": { "x-api-key": "HASDATA_API_KEY" }
    }
  }
}

工作区中的 .vscode/mcp.json

{
  "servers": {
    "google-flights": {
      "type": "http",
      "url": "https://mcp.hasdata.com/api/mcp?apis=google_travel_flights",
      "headers": { "x-api-key": "HASDATA_API_KEY" }
    }
  }
}

示例提示

这些是提示词,不是代码。粘贴一条,智能体会自己选择工具。每条都标注了需要的调用次数,因为每次成功调用消耗 15 积分。

查找 9 月 15 日从 JFK 飞往伦敦希思罗的单程航班,按价格排序,并给我最便宜的三趟,包含航空公司和碳排放估算。

一次调用,15 积分。票价、航段和排放量会一起返回。

同一路线,但仅直飞、公务舱,并告诉我哪个选项的碳排放最低。

一次调用,15 积分。舱位和中转次数都是同一次请求中的筛选条件。

考虑到价格历史,现在 JFK 到 LHR 的 295 美元是不是好价格?

一次调用,15 积分。响应会携带 priceInsights,包含典型价格区间和价格水平。

JFK 到 LHR 往返,9 月 15 日去、9 月 22 日回,最便宜的票价。

两次调用,30 积分。Google 先返回去程选项,然后根据你选择的选项,第二次调用获取对应的返程航段。

往返行程按设计需要两次调用。第一次返回去程行程,每个行程带一个 departureToken;你把该令牌传回去,就能获得匹配的返程航班。单程和价格查询各只需一次调用。

工具

一个只读工具。下面的示例截取自一次真实调用并做了删减,而且票价时刻在变动。把它当作一种结构示例来看。工具名称链接到其端点参考文档,其中包含完整的参数列表。

该示例是载荷(payload),不是完整响应。tools/call 的结果包含一个文本块,而该文本本身是 JSON,包含 urlstatustextjson,抓取的数据位于 json 之下。从原始 JSON-RPC 响应来看,路径是 result.content[0].text,解析后再取 .json。聊天客户端会为你解包;直接与端点通信的代码则不会。

获取 Google Flights 结果

hasdata_google_travel_flights_getGoogleFlights

返回某条航线在指定日期的行程,包含票价、航段、碳排放和价格历史。

参数

类型

必填

说明

departureId

string

IATA 代码,如 JFK;或位置 kgmid,如 /m/02_286。多个机场用逗号分隔

arrivalId

string

格式同 departureId

outboundDate

string

YYYY-MM-DD

type

string

默认为 roundTriponeWay,或与 multiCityJson 配合的 multiCity

returnDate

string

typeroundTrip 时必填

travelClass

string

economypremiumEconomybusinessfirst

stops

string

nonStoponeStopOrFewertwoStopsOrFewer

sortBy

string

默认为 topFlights,另有 pricedurationemissionsdepartureTimearrivalTime

adults / children / infantsInSeat / infantsOnLap

number

乘客组合

maxPrice / maxDuration / bags

number

上限及随身行李数量

includeAirlines / excludeAirlines

string

逗号分隔的 IATA 航空公司代码,二者选一,不能同时使用

departureToken

string

选择一个去程选项,并获取其返程或下一段航段

bookingToken

string

获取所选行程的预订选项

currency / gl / hl

string

货币,以及搜索的国家和语言

deepSearch

boolean

与浏览器中 Google 显示的结果一致,返回更慢

参考文档还记录了 includeConnectionsexcludeConnectionslayoverDurationoutboundTimesreturnTimesshowHiddenlessEmissionsmultiCityJson

结果分为 bestFlightsotherFlights。每个行程包含 pricetype、以分钟为单位的 totalDuration、一个由航段组成的 flights 数组、一个 carbonEmissions 对象,以及一个 bookingToken。每个航段包含 departureAirportarrivalAirport(各自带有 idname 和当地 time),以及 durationairlineflightNumberairplanelegroomtravelClass、一个 extensions 数组,以及 Google 标记航段上的 oftenDelayedByOver30Min。直飞行程只有一个航段,中转行程则有多个航段。

carbonEmissions 的单位是克,不是千克。thisFlight: 433000 即 433 千克。differencePercent 将它与 typicalForThisRoute 比较,因此负数表示比平均航班更环保。

{
  "price": 295,
  "type": "One way",
  "totalDuration": 415,
  "flights": [
    {
      "departureAirport": { "id": "JFK", "name": "John F. Kennedy International Airport", "time": "2026-09-15 8:15" },
      "arrivalAirport": { "id": "LHR", "name": "Heathrow Airport", "time": "2026-09-15 20:10" },
      "duration": 415,
      "airline": "Virgin Atlantic",
      "flightNumber": "VS 26",
      "airplane": "Boeing 787",
      "travelClass": "Economy"
    }
  ],
  "carbonEmissions": { "thisFlight": 367000, "typicalForThisRoute": 419000, "differencePercent": -12 },
  "bookingToken": "W1t7..."
}

priceInsights 与行程列表并列,包含 lowestPricetypicalPriceRange、类似 typicalpriceLevel,以及由 [timestamp, price] 数据点组成的 priceHistoryairports 会回显解析后的出发机场和到达机场,并包含城市和国家。

错误与失败路径

你的客户端几乎不会在工具调用中看到 HTTP 错误码。MCP 层会返回 200,并把失败信息放在结果内部,isError 设为 true,原因以文本形式呈现。在你可能预期看到状态行的地方,智能体读到的是一条消息。

错误的密钥会以工具输出的形式出现,而不是连接失败。 tools/list 接受任何非空密钥并返回工具,因此客户端能完成握手并显示绿色。第一次工具调用随后返回 isError: true,文本为 HasData API error: 401。请留意这个字符串,因为流程中早先没有任何环节会报告该问题。

缺少密钥是唯一真正的 HTTP 错误。 授权在任何工具之前执行,连接本身会以 401 失败。CORS 头存在,浏览器客户端能读取状态,而不是得到一个不透明的网络错误。

破坏工具 schema 的参数会在变成抓取请求之前被拒绝。 服务器返回 isError: true,文本为 MCP error -32602: Input validation error,并指出出错的字段。没有 returnDateroundTrip,或者 includeAirlinesexcludeAirlines 同时出现,都会在这里被拦截。

某日期航线上没有航班时,会返回一个成功结果,但行程数组为空,而不是错误。requestMetadata.status 仍为 ok。在对航班排序之前,请先检查是否存在航班。

错误的机场代码会返回 400,其中 requestMetadata.status 设置为 error。请使用 IATA 代码或 kgmids,而不是城市名称。

携带数据的结果还会带有 requestMetadata.id,在联系支持时值得附上。

定价、免费套餐和限制

每次成功的 Google Flights 调用需要 15 个积分。响应大小不会改变价格,深度搜索与标准搜索费用相同。

免费试用为 30 天内 1,000 个积分,无需绑定银行卡,大约相当于 66 次航班搜索。之后,只要活跃账户的余额低于 100,系统每天都会为其补充 100 个积分,因此低流量智能体可以无限期运行在免费套餐上。

付费套餐起价为 每月 $49,提供 200,000 个积分,大约相当于 13,000 次搜索。单价随用量下降,从入门套餐的 每 1,000 次调用 $3.68,到 Business 的 $1.49、Growth 的 $1.25,以及最大 高用量套餐$1.12

你的套餐还设定了并发限制。免费试用允许同时 1 个请求,Startup 15 个,Business 30 个,Growth 50 个,高用量套餐为 200 到 1,500 个。在任何无人值守的程序中都要防御性地处理溢出情况。

返回非 200 的请求不会计费。往返行程是两次调用,所以要为此做好预算。

工具选择

apis 查询参数决定你的智能体可以看到哪些工具。工具越少,用于工具定义的上下文就越少,模型选错工具的机会也就越小。

?apis=google_travel_flights          the one tool in this repo
?apis=google_travel                   add Google Hotels
?apis=google_travel_flights,airbnb    flights plus Airbnb stays

该参数接受提供方名称,如 google_travel,以及单个 API 名称,如 google_travel_flights。拼写错误的名称会被忽略。如果所有名称都错误,请求会以 400 失败,响应体会列出它无法识别的名称以及所有有效值。省略该参数后,同一端点会暴露全部 57 个 HasData 工具。

对比

Google 于 2018 年退役了 QPX Express 航班 API,并且从未推出替代品,因此没有官方的 Google Flights API。剩下的路径是抓取公开结果,或获取原始 GDS 票价数据的授权,后者既笨重又昂贵。此服务器读取网站展示的相同结果,并以 JSON 形式返回。

官方 Google API

本服务器

可用性

自 QPX Express 于 2018 年关闭后就没有

对实时结果维护的 schema

排放数据

不提供

按行程提供,并与航线平均值比较

价格历史

不提供

priceInsights 附带典型价格区间

设置

无需设置,因为它不存在

一个密钥和一个 URL

成本

不适用

试用期后付费,每次调用 15 个积分

此服务器不做什么。 不提供预订,也不处理付款。它读取票价、航段以及 Google 自身用于跳转到预订流程的 token,并把预订步骤交还给你。

常见问题

有官方的 Google Flights API 吗?

没有。Google 于 2018 年关闭了 QPX Express,并且没有推出替代品。所有方案读取的都是网站提供的同一份公开结果。本方案由 HasData 维护,并以结构化 JSON 返回这些结果。

什么是 Google Flights MCP 服务器?

这是一种将 Google Flights 作为可供 AI 客户端调用的工具来暴露的服务器。客户端通过 Model Context Protocol 发送工具调用,服务器获取行程并以结构化 JSON 返回,模型再处理该结果。本服务器暴露单个工具,并且远程运行。

为什么往返行程是两次调用?

Google 先返回去程选项,每个选项带有一个 departureToken。你选择一个,并把这个 token 传回,以获取与之配对的返程航班。这与网站的工作方式一致,也是往返行程需要 30 个积分的原因。

碳排数字的单位是千克吗?

不,是克。thisFlight: 433000 表示 433 kg,differencePercent 将其与航线平均值进行比较。

什么是深度搜索?

一种较慢的模式,返回的内容与 Google Flights 在浏览器中显示的内容完全一致。为了速度可以关闭它;当需要与网站保持一致时再开启。

我可以将它与其它 HasData API 一起使用吗?

可以。apis 参数接受一个列表,?apis=google_travel 会在航班之外加上 Google Hotels。省略该参数,你会获得所有工具。

合规性与个人数据

HasData 仅访问公开可用的数据。平台的服务条款可能限制自动访问,你需要自行负责合规。

HasData 链接

产品页面和请求构建器

Google Flights API

服务器文档

MCP 服务器文档

一个服务器中的全部 57 个工具

HasData/hasdata-mcp

客户端入门指南

MCP 客户端与集成

我们抓取的其他所有内容

Google Flights API 及其余 54 个

套餐和积分费用

套餐和积分费用

密钥与用量

HasData 控制面板

npm 上的 Node 启动器

@hasdata/google-flights-mcp

PyPI 上的 Python 启动器

hasdata-google-flights-mcp

开发

该仓库是远程服务器的配置和文档。没有构建步骤,也无需容器化。

test/ 中的测试断言工具契约,即即使本仓库没有提交也可能出问题的部分。它们检查 ?apis=google_travel_flights 是否恰好返回一个工具、是否仍声明其必填参数、名称是否未变,以及正在使用的密钥是否确实被接受。最后一项检查会真实调用该工具并花费 15 个积分,这正是金丝雀测试能够因正确原因而失败的代价。

# macOS and Linux
HASDATA_API_KEY=your_key_here npm test

# Windows PowerShell
$env:HASDATA_API_KEY="your_key_here"; npm test

同一套测试会在每次推送时于 CI 中运行,并按计划每周运行一次,因为即使没有人改动本仓库,上游工具列表也可能发生变化。失败意味着工具列表变了、密钥失效了,或者端点无法访问,断言消息会说明具体是哪一种。

贡献

对参数表和响应示例的修正是最有用的贡献,因为这些部分最容易漂移。请附上你发出的调用和收到的响应。来自 fork 的 Pull Request 会在没有密钥的情况下运行测试套件,在线检查会跳过而不会报红。

许可证

MIT。参见 LICENSE

Available Tools

1 tool
hasdata_google_travel_flights_getGoogleFlightsgoogle_travel_flights: GET /AInspect

Get Google Flights Results

Searches Google Flights for one-way, round-trip, or multi-city itineraries with passenger mix (adults, children, infants in-seat/on-lap), travel class, bags, max price, sort order (price, duration, emissions, departure/arrival time), stops, include/exclude airlines and connections, time windows, layover duration, and deep-search mode. Returns per-itinerary price, currency, total duration, stops, flight legs with airline, flight number, aircraft, departure/arrival airports and times, CO2 emissions, plus booking and departure tokens for round-trip returns or booking options. Use for travel-planning agents, fare monitoring, corporate travel dashboards, emission-aware trip optimization, and comparing routes and airlines across markets.

ParametersJSON Schema
NameRequiredDescriptionDefault
glNoThe two-letter country code for the country you want to limit the search to. Provide one exact documented value (245 allowed), e.g. `ac`, `af`.
hlNoThe two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`.
bagsNoNumber of carry-on bags per passenger.
typeNoSpecifies the type of flight. Options: - `roundTrip` (default) - `oneWay` - `multiCity` (requires `multiCityJson` for flight details) For round trips, retrieve return flight details with a separate request using `departureToken`.
stopsNoRestrict the number of stops (layovers) in the flight itinerary.
adultsNoNumber of adult passengers (>= 1 if specified).
sortByNoSort the flight results based on price, departure time, arrival time, etc.
childrenNoNumber of child passengers.
currencyNoParameter defines the currency of the returned prices Provide one exact documented value (71 allowed), e.g. `ALL`, `DZD`.
maxPriceNoMaximum price limit for the flight search, in the selected currency.
arrivalIdYesSpecifies the arrival airport code (IATA) or location kgmid. - **IATA Code**: A 3-letter uppercase code (e.g., `SFO` for San Francisco, `LHR` for London Heathrow). Search on [IATA](https://www.iata.org/en/publications/directories/code-search). - **Location kgmid**: A string starting with `/m/`, found in Wikidata under "Freebase ID" (e.g., `/m/02_286` for New York, NY). Multiple values can be separated by commas (e.g., `JFK,LGA,/m/0hptm`).
deepSearchNoEnable deep search. Returns the same results as Google Flights in a browser, but takes longer to respond. Default is `false`.
returnDateNoThe return travel date in 'yyyy-MM-dd' format. Required when **type** is `roundTrip`.
showHiddenNoIndicates whether to include hidden options in the results.
departureIdYesSpecifies the departure airport code (IATA) or location kgmid. - **IATA Code**: A 3-letter uppercase code (e.g., SFO for San Francisco, LHR for London Heathrow). Search on [IATA](https://www.iata.org/en/publications/directories/code-search). - **Location kgmid**: A string starting with `/m/`, found in Wikidata under "Freebase ID" (e.g., `/m/02_286` for New York, NY). Multiple values can be separated by commas (e.g., `JFK,LGA,/m/0hptm`).
maxDurationNoThe maximum total flight duration in minutes.
returnTimesNoSet up to 4 time boundaries (2 for departure, 2 for arrival) to filter return flights. Each number represents the start of an hour. Examples: - `6,20` → 6:00 AM - 9:00 PM departure - `1,15` → 1:00 AM - 4:00 PM departure - `7,18,2,21` → 7:00 AM - 9:00 PM departure, 2:00 AM - 10:00 PM arrival
travelClassNoThe travel class for the flight (Economy, Premium Economy, Business, or First).
bookingTokenNoUsed to request booking options for selected flights. This token is found in the flight results and cannot be used with `departureToken`.
infantsOnLapNoNumber of infants sitting on an adult's lap.
outboundDateYesThe outbound travel date in 'yyyy-MM-dd' format.
infantsInSeatNoNumber of infants occupying seats.
lessEmissionsNoPrefer flight options with lower carbon emissions.
multiCityJsonNoThis parameter specifies flight details for multi-city trips. It is a JSON string containing multiple flight objects. Each object must include the following fields: - **departureId** – The departure airport code or location KGMID. Uses the same format as the main `departureId` parameter. - **arrivalId** – The arrival airport code or location KGMID. Uses the same format as the main `arrivalId` parameter. - **date** – The flight date. Uses the same format as the `outboundDate` parameter. - **times** *(optional)* – The time range for the flight. Uses the same format as the `outboundTimes` parameter.
outboundTimesNoSet up to 4 time boundaries (2 for departure, 2 for arrival) to filter flights. Each number represents the start of an hour. Examples: - `6,20` → 6:00 AM - 9:00 PM departure - `1,15` → 1:00 AM - 4:00 PM departure - `7,18,2,21` → 7:00 AM - 9:00 PM departure, 2:00 AM - 10:00 PM arrival
departureTokenNoUsed to select a flight and retrieve return flights for a round trip or the next leg of the itinerary for a multi-city trip.
excludeAirlinesNoA comma separated list of airline codes to exclude from results. You can search for airline codes on [IATA](https://www.iata.org/en/publications/directories/code-search). For example, `UA` is United Airlines.
includeAirlinesNoA comma separated list of airline codes to exclusively include in results. You can search for airline codes on [IATA](https://www.iata.org/en/publications/directories/code-search). For example, `UA` is United Airlines. `excludeAirlines` and `includeAirlines` parameters can't be used together.
layoverDurationNoSet the maximum layover duration in minutes to filter flights. For example, `120, 360` filters layovers between 2 hours and 6 hours, while `45, 180` allows layovers from 45 minutes to 3 hours.
excludeConnectionsNoA comma separated list of specific airports to exclude as connections.
includeConnectionsNoA comma separated list of specific airports to allow as connections.

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden for behavioral disclosure. It states what the search returns and implies a read-only operation, but it does not explicitly mention that no mutations occur, nor does it disclose rate limits, latency differences beyond the per-parameter deepSearch note, or any operational constraints such as result limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and uses three focused sentences covering operation, returned data, and use cases. The final use-case list includes some reputation-heavy phrases, but for 31 parameters the summary remains scannable and does not repeat schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description's enumeration of returned per-itinerary fields is valuable and largely covers the response contract. Input parameters are fully documented in the schema with examples. The main gaps are the lack of pagination/error behavior and some explanation of how booking and departure tokens should be used, but these are partially covered by parameter descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the input schema. The description only groups parameter types into a summary and adds no new per-parameter semantics, yielding the baseline score for a fully covered schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Searches Google Flights') and a clear resource, and goes beyond the name by enumerating trip types, filter dimensions, and returned data. An agent can immediately understand what this tool does and what its result contract looks like.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit use contexts ('travel-planning agents, fare monitoring, corporate travel dashboards, emission-aware trip optimization') and covers the major itinerary types. There are no sibling tools to compare against, so explicit when-not-to-use or alternative routing is not possible, but the intended use cases are clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • First observedhasdata_google_travel_flights_getGoogleFlights

TDQS

A3.9/5.0
Disambiguation5/5

With only one tool present, there is no possibility of an agent confusing it with another tool. The lone tool is clearly described as the only way to search Google Flights results.

Naming Consistency3/5

The single tool name mixes a snake_case provider/domain prefix with a camelCase verb phrase, which is internally inconsistent. Since there is only one tool, there is no broader set of names to establish a consistent pattern, so the score is moderate.

Tool Count3/5

A single tool for a flight-search MCP server is borderline; it is not a trivial tool, but the surface feels thin for a server that could plausibly support fare calendars, route metadata, or booking workflows. The count is acceptable but not well-rounded.

Completeness4/5

The one tool covers a wide range of search options, including itinerary types, passenger mix, class, bags, price, stops, airlines, time windows, and emissions. For its stated purpose of getting Google Flights search results, it is quite complete, though auxiliary endpoints like airport lookup or flight status are absent.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • -
    license
    Not graded
    quality
    Not graded
    maintenance
    Enables searching and retrieving flight information using Duffel API, supporting one-way, round-trip, and multi-city queries with flexible search parameters.
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI clients to explore cheapest destinations, optimize multi-leg flight itineraries, and reference airport/region data via MCP tools and resources.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables MCP clients to query the Seats.aero partner API for seat availability, trips, routes, and destinations, including cached and live search options.
    101
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HasData/google-flights-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server